< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 6 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0004

Data Index: 516743 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0744. Min Act: -0.0004

Data Index: 391995 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0671. Min Act: -0.0004

Data Index: 1307466 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0694. Min Act: -0.0004

Data Index: 1800011 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0642. Min Act: -0.0004

Data Index: 705531 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0637. Min Act: -0.0004

Data Index: 260595 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0624. Min Act: -0.0004

Data Index: 1799834 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0560. Min Act: -0.0004

Data Index: 1188383 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0572. Min Act: -0.0004

Data Index: 768512 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0577. Min Act: -0.0004

Data Index: 1407324 (The Pile)

Max Activating Token Index: 660

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0633. Min Act: -0.0004

Data Index: 496047 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0559. Min Act: -0.0004

Data Index: 183860 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0567. Min Act: -0.0004

Data Index: 234953 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0587. Min Act: -0.0004

Data Index: 368849 (The Pile)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0538. Min Act: -0.0004

Data Index: 133866 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0542. Min Act: -0.0004

Data Index: 844828 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0533. Min Act: -0.0004

Data Index: 214175 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0519. Min Act: -0.0004

Data Index: 519182 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0539. Min Act: -0.0004

Data Index: 878448 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0550. Min Act: -0.0004

Data Index: 926114 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #19